comparison tests/test-manifest.py @ 47043:12450fbea288

manifests: push down expected node length into the parser

This strictly enforces the node length in the manifest lines according
to what the repository expects. One test case moves large hash testing
into the non-treemanifest part as treemanifests don't provide an
interface for overriding just the node length for now.

Differential Revision: https://phab.mercurial-scm.org/D10533

47042:c5e1cc0b4c77

class basemanifesttests(object):
    def parsemanifest(self, text):
        raise NotImplementedError('parsemanifest not implemented by test case')

    def testEmptyManifest(self):
        m = self.parsemanifest(EMTPY_MANIFEST)
        self.assertEqual(0, len(m))
        self.assertEqual([], list(m))

    def testManifest(self):
        m = self.parsemanifest(A_SHORT_MANIFEST)
        self.assertEqual([b'bar/baz/qux.py', b'foo'], list(m))
        self.assertEqual(BIN_HASH_2, m[b'bar/baz/qux.py'])
        self.assertEqual(b'l', m.flags(b'bar/baz/qux.py'))
        self.assertEqual(BIN_HASH_1, m[b'foo'])
        self.assertEqual(b'', m.flags(b'foo'))
        with self.assertRaises(KeyError):
            m[b'wat']

    def testManifestLongHashes(self):
        m = self.parsemanifest(b'a\0' + b'f' * 64 + b'\n')
        self.assertEqual(binascii.unhexlify(b'f' * 64), m[b'a'])

    def testSetItem(self):
        want = BIN_HASH_1

        m = self.parsemanifest(EMTPY_MANIFEST)
        m[b'a'] = want
        self.assertIn(b'a', m)
        self.assertEqual(want, m[b'a'])
        self.assertEqual(b'a\0' + HASH_1 + b'\n', m.text())

        m = self.parsemanifest(A_SHORT_MANIFEST)
        m[b'a'] = want
        self.assertEqual(want, m[b'a'])
        self.assertEqual(b'a\0' + HASH_1 + b'\n' + A_SHORT_MANIFEST, m.text())

    def testSetFlag(self):
        want = b'x'

        m = self.parsemanifest(EMTPY_MANIFEST)
        # first add a file; a file-less flag makes no sense
        m[b'a'] = BIN_HASH_1
        m.setflag(b'a', want)
        self.assertEqual(want, m.flags(b'a'))
        self.assertEqual(b'a\0' + HASH_1 + want + b'\n', m.text())

        m = self.parsemanifest(A_SHORT_MANIFEST)
        # first add a file; a file-less flag makes no sense
        m[b'a'] = BIN_HASH_1
        m.setflag(b'a', want)
        self.assertEqual(want, m.flags(b'a'))
        self.assertEqual(
            b'a\0' + HASH_1 + want + b'\n' + A_SHORT_MANIFEST, m.text()
        )

    def testCopy(self):
        m = self.parsemanifest(A_SHORT_MANIFEST)
        m[b'a'] = BIN_HASH_1
        m2 = m.copy()
        del m
        del m2  # make sure we don't double free() anything

    def testCompaction(self):
        unhex = binascii.unhexlify
        h1, h2 = unhex(HASH_1), unhex(HASH_2)
        m = self.parsemanifest(A_SHORT_MANIFEST)
        m[b'alpha'] = h1
        m[b'beta'] = h2
        del m[b'foo']
        want = b'alpha\0%s\nbar/baz/qux.py\0%sl\nbeta\0%s\n' % (
            HASH_1,

        self.assertEqual(b'', m.flags(b'beta'))
        with self.assertRaises(KeyError):
            m[b'foo']

    def testMatchException(self):
        m = self.parsemanifest(A_SHORT_MANIFEST)
        match = matchmod.match(util.localpath(b'/repo'), b'', [b're:.*'])

        def filt(path):
            if path == b'foo':
                assert False

        match.matchfn = filt
        with self.assertRaises(AssertionError):
            m._matches(match)

    def testRemoveItem(self):
        m = self.parsemanifest(A_SHORT_MANIFEST)
        del m[b'foo']
        with self.assertRaises(KeyError):
            m[b'foo']
        self.assertEqual(1, len(m))
        self.assertEqual(1, len(list(m)))

    def testManifestDiff(self):
        MISSING = (None, b'')
        addl = b'z-only-in-left\0' + HASH_1 + b'\n'
        addr = b'z-only-in-right\0' + HASH_2 + b'x\n'
        left = self.parsemanifest(
            A_SHORT_MANIFEST.replace(HASH_1, HASH_3 + b'x') + addl
        )
        right = self.parsemanifest(A_SHORT_MANIFEST + addr)
        want = {
            b'foo': ((BIN_HASH_3, b'x'), (BIN_HASH_1, b'')),
            b'z-only-in-left': ((BIN_HASH_1, b''), MISSING),
            b'z-only-in-right': (MISSING, (BIN_HASH_2, b'x')),
        }

        want = {
            b'bar/baz/qux.py': (MISSING, (BIN_HASH_2, b'l')),
            b'foo': (MISSING, (BIN_HASH_3, b'x')),
            b'z-only-in-left': (MISSING, (BIN_HASH_1, b'')),
        }
        self.assertEqual(want, self.parsemanifest(EMTPY_MANIFEST).diff(left))

        want = {
            b'bar/baz/qux.py': ((BIN_HASH_2, b'l'), MISSING),
            b'foo': ((BIN_HASH_3, b'x'), MISSING),
            b'z-only-in-left': ((BIN_HASH_1, b''), MISSING),
        }
        self.assertEqual(want, left.diff(self.parsemanifest(EMTPY_MANIFEST)))
        copy = right.copy()
        del copy[b'z-only-in-right']
        del right[b'foo']
        want = {
            b'foo': (MISSING, (BIN_HASH_1, b'')),
            b'z-only-in-right': ((BIN_HASH_2, b'x'), MISSING),
        }
        self.assertEqual(want, right.diff(copy))

        short = self.parsemanifest(A_SHORT_MANIFEST)
        pruned = short.copy()
        del pruned[b'foo']
        want = {
            b'foo': ((BIN_HASH_1, b''), MISSING),
        }

    def testReversedLines(self):
        backwards = b''.join(
            l + b'\n' for l in reversed(A_SHORT_MANIFEST.split(b'\n')) if l
        )
        try:
            self.parsemanifest(backwards)
            self.fail('Should have raised ValueError')
        except ValueError as v:
            self.assertIn('Manifest lines not in sorted order.', str(v))

    def testNoTerminalNewline(self):
        try:
            self.parsemanifest(A_SHORT_MANIFEST + b'wat')
            self.fail('Should have raised ValueError')
        except ValueError as v:
            self.assertIn('Manifest did not end in a newline.', str(v))

    def testNoNewLineAtAll(self):
        try:
            self.parsemanifest(b'wat')
            self.fail('Should have raised ValueError')
        except ValueError as v:
            self.assertIn('Manifest did not end in a newline.', str(v))

    def testHugeManifest(self):
        m = self.parsemanifest(A_HUGE_MANIFEST)
        self.assertEqual(HUGE_MANIFEST_ENTRIES, len(m))
        self.assertEqual(len(m), len(list(m)))

    def testMatchesMetadata(self):
        """Tests matches() for a few specific files to make sure that both
        the set of files as well as their flags and nodeids are correct in
        the resulting manifest."""
        m = self.parsemanifest(A_HUGE_MANIFEST)

        match = matchmod.exact([b'file1', b'file200', b'file300'])
        m2 = m._matches(match)

        w = (b'file1\0%sx\n' b'file200\0%sl\n' b'file300\0%s\n') % (

    def testMatchesNonexistentFile(self):
        """Tests matches() for a small set of specific files, including one
        nonexistent file to make sure in only matches against existing files.
        """
        m = self.parsemanifest(A_DEEPER_MANIFEST)

        match = matchmod.exact(
            [b'a/b/c/bar.txt', b'a/b/d/qux.py', b'readme.txt', b'nonexistent']
        )
        m2 = m._matches(match)

        )

    def testMatchesNonexistentDirectory(self):
        """Tests matches() for a relpath match on a directory that doesn't
        actually exist."""
        m = self.parsemanifest(A_DEEPER_MANIFEST)

        match = matchmod.match(
            util.localpath(b'/repo'), b'', [b'a/f'], default=b'relpath'
        )
        m2 = m._matches(match)

        self.assertEqual([], m2.keys())

    def testMatchesExactLarge(self):
        """Tests matches() for files matching a large list of exact files."""
        m = self.parsemanifest(A_HUGE_MANIFEST)

        flist = m.keys()[80:300]
        match = matchmod.exact(flist)
        m2 = m._matches(match)

        self.assertEqual(flist, m2.keys())

    def testMatchesFull(self):
        '''Tests matches() for what should be a full match.'''
        m = self.parsemanifest(A_DEEPER_MANIFEST)

        match = matchmod.match(util.localpath(b'/repo'), b'', [b''])
        m2 = m._matches(match)

        self.assertEqual(m.keys(), m2.keys())

    def testMatchesDirectory(self):
        """Tests matches() on a relpath match on a directory, which should
        match against all files within said directory."""
        m = self.parsemanifest(A_DEEPER_MANIFEST)

        match = matchmod.match(
            util.localpath(b'/repo'), b'', [b'a/b'], default=b'relpath'
        )
        m2 = m._matches(match)

    def testMatchesExactPath(self):
        """Tests matches() on an exact match on a directory, which should
        result in an empty manifest because you can't perform an exact match
        against a directory."""
        m = self.parsemanifest(A_DEEPER_MANIFEST)

        match = matchmod.exact([b'a/b'])
        m2 = m._matches(match)

        self.assertEqual([], m2.keys())

    def testMatchesCwd(self):
        """Tests matches() on a relpath match with the current directory ('.')
        when not in the root directory."""
        m = self.parsemanifest(A_DEEPER_MANIFEST)

        match = matchmod.match(
            util.localpath(b'/repo'), b'a/b', [b'.'], default=b'relpath'
        )
        m2 = m._matches(match)

        )

    def testMatchesWithPattern(self):
        """Tests matches() for files matching a pattern that reside
        deeper than the specified directory."""
        m = self.parsemanifest(A_DEEPER_MANIFEST)

        match = matchmod.match(util.localpath(b'/repo'), b'', [b'a/b/*/*.txt'])
        m2 = m._matches(match)

        self.assertEqual(
            [b'a/b/c/bar.txt', b'a/b/c/foo.txt', b'a/b/d/ten.txt'], m2.keys()
        )


class testmanifestdict(unittest.TestCase, basemanifesttests):
    def parsemanifest(self, text):
        return manifestmod.manifestdict(text)

    def testObviouslyBogusManifest(self):
        # This is a 163k manifest that came from oss-fuzz. It was a
        # timeout there, but when run normally it doesn't seem to
        # present any particular slowness.

            b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00'
            b'\x00\x00\xc0\x8aey\x1d}\x01\xd8\xe0\xb9\xf3\xde\x1b\xcf\x17'
            b'\xac\xbe'
        )
        with self.assertRaises(ValueError):
            self.parsemanifest(data)


class testtreemanifest(unittest.TestCase, basemanifesttests):
    def parsemanifest(self, text):
        return manifestmod.treemanifest(sha1nodeconstants, b'', text)

    def testWalkSubtrees(self):
        m = self.parsemanifest(A_DEEPER_MANIFEST)

        dirs = [s._dir for s in m.walksubtrees()]
        self.assertEqual(
            sorted(
                [b'', b'a/', b'a/c/', b'a/d/', b'a/b/', b'a/b/c/', b'a/b/d/']

47043:12450fbea288

class basemanifesttests(object):
    def parsemanifest(self, text):
        raise NotImplementedError('parsemanifest not implemented by test case')

    def testEmptyManifest(self):
        m = self.parsemanifest(20, EMTPY_MANIFEST)
        self.assertEqual(0, len(m))
        self.assertEqual([], list(m))

    def testManifest(self):
        m = self.parsemanifest(20, A_SHORT_MANIFEST)
        self.assertEqual([b'bar/baz/qux.py', b'foo'], list(m))
        self.assertEqual(BIN_HASH_2, m[b'bar/baz/qux.py'])
        self.assertEqual(b'l', m.flags(b'bar/baz/qux.py'))
        self.assertEqual(BIN_HASH_1, m[b'foo'])
        self.assertEqual(b'', m.flags(b'foo'))
        with self.assertRaises(KeyError):
            m[b'wat']

    def testSetItem(self):
        want = BIN_HASH_1

        m = self.parsemanifest(20, EMTPY_MANIFEST)
        m[b'a'] = want
        self.assertIn(b'a', m)
        self.assertEqual(want, m[b'a'])
        self.assertEqual(b'a\0' + HASH_1 + b'\n', m.text())

        m = self.parsemanifest(20, A_SHORT_MANIFEST)
        m[b'a'] = want
        self.assertEqual(want, m[b'a'])
        self.assertEqual(b'a\0' + HASH_1 + b'\n' + A_SHORT_MANIFEST, m.text())

    def testSetFlag(self):
        want = b'x'

        m = self.parsemanifest(20, EMTPY_MANIFEST)
        # first add a file; a file-less flag makes no sense
        m[b'a'] = BIN_HASH_1
        m.setflag(b'a', want)
        self.assertEqual(want, m.flags(b'a'))
        self.assertEqual(b'a\0' + HASH_1 + want + b'\n', m.text())

        m = self.parsemanifest(20, A_SHORT_MANIFEST)
        # first add a file; a file-less flag makes no sense
        m[b'a'] = BIN_HASH_1
        m.setflag(b'a', want)
        self.assertEqual(want, m.flags(b'a'))
        self.assertEqual(
            b'a\0' + HASH_1 + want + b'\n' + A_SHORT_MANIFEST, m.text()
        )

    def testCopy(self):
        m = self.parsemanifest(20, A_SHORT_MANIFEST)
        m[b'a'] = BIN_HASH_1
        m2 = m.copy()
        del m
        del m2  # make sure we don't double free() anything

    def testCompaction(self):
        unhex = binascii.unhexlify
        h1, h2 = unhex(HASH_1), unhex(HASH_2)
        m = self.parsemanifest(20, A_SHORT_MANIFEST)
        m[b'alpha'] = h1
        m[b'beta'] = h2
        del m[b'foo']
        want = b'alpha\0%s\nbar/baz/qux.py\0%sl\nbeta\0%s\n' % (
            HASH_1,

        self.assertEqual(b'', m.flags(b'beta'))
        with self.assertRaises(KeyError):
            m[b'foo']

    def testMatchException(self):
        m = self.parsemanifest(20, A_SHORT_MANIFEST)
        match = matchmod.match(util.localpath(b'/repo'), b'', [b're:.*'])

        def filt(path):
            if path == b'foo':
                assert False

        match.matchfn = filt
        with self.assertRaises(AssertionError):
            m._matches(match)

    def testRemoveItem(self):
        m = self.parsemanifest(20, A_SHORT_MANIFEST)
        del m[b'foo']
        with self.assertRaises(KeyError):
            m[b'foo']
        self.assertEqual(1, len(m))
        self.assertEqual(1, len(list(m)))

    def testManifestDiff(self):
        MISSING = (None, b'')
        addl = b'z-only-in-left\0' + HASH_1 + b'\n'
        addr = b'z-only-in-right\0' + HASH_2 + b'x\n'
        left = self.parsemanifest(
            20, A_SHORT_MANIFEST.replace(HASH_1, HASH_3 + b'x') + addl
        )
        right = self.parsemanifest(20, A_SHORT_MANIFEST + addr)
        want = {
            b'foo': ((BIN_HASH_3, b'x'), (BIN_HASH_1, b'')),
            b'z-only-in-left': ((BIN_HASH_1, b''), MISSING),
            b'z-only-in-right': (MISSING, (BIN_HASH_2, b'x')),
        }

        want = {
            b'bar/baz/qux.py': (MISSING, (BIN_HASH_2, b'l')),
            b'foo': (MISSING, (BIN_HASH_3, b'x')),
            b'z-only-in-left': (MISSING, (BIN_HASH_1, b'')),
        }
        self.assertEqual(
            want, self.parsemanifest(20, EMTPY_MANIFEST).diff(left)
        )

        want = {
            b'bar/baz/qux.py': ((BIN_HASH_2, b'l'), MISSING),
            b'foo': ((BIN_HASH_3, b'x'), MISSING),
            b'z-only-in-left': ((BIN_HASH_1, b''), MISSING),
        }
        self.assertEqual(
            want, left.diff(self.parsemanifest(20, EMTPY_MANIFEST))
        )
        copy = right.copy()
        del copy[b'z-only-in-right']
        del right[b'foo']
        want = {
            b'foo': (MISSING, (BIN_HASH_1, b'')),
            b'z-only-in-right': ((BIN_HASH_2, b'x'), MISSING),
        }
        self.assertEqual(want, right.diff(copy))

        short = self.parsemanifest(20, A_SHORT_MANIFEST)
        pruned = short.copy()
        del pruned[b'foo']
        want = {
            b'foo': ((BIN_HASH_1, b''), MISSING),
        }

    def testReversedLines(self):
        backwards = b''.join(
            l + b'\n' for l in reversed(A_SHORT_MANIFEST.split(b'\n')) if l
        )
        try:
            self.parsemanifest(20, backwards)
            self.fail('Should have raised ValueError')
        except ValueError as v:
            self.assertIn('Manifest lines not in sorted order.', str(v))

    def testNoTerminalNewline(self):
        try:
            self.parsemanifest(20, A_SHORT_MANIFEST + b'wat')
            self.fail('Should have raised ValueError')
        except ValueError as v:
            self.assertIn('Manifest did not end in a newline.', str(v))

    def testNoNewLineAtAll(self):
        try:
            self.parsemanifest(20, b'wat')
            self.fail('Should have raised ValueError')
        except ValueError as v:
            self.assertIn('Manifest did not end in a newline.', str(v))

    def testHugeManifest(self):
        m = self.parsemanifest(20, A_HUGE_MANIFEST)
        self.assertEqual(HUGE_MANIFEST_ENTRIES, len(m))
        self.assertEqual(len(m), len(list(m)))

    def testMatchesMetadata(self):
        """Tests matches() for a few specific files to make sure that both
        the set of files as well as their flags and nodeids are correct in
        the resulting manifest."""
        m = self.parsemanifest(20, A_HUGE_MANIFEST)

        match = matchmod.exact([b'file1', b'file200', b'file300'])
        m2 = m._matches(match)

        w = (b'file1\0%sx\n' b'file200\0%sl\n' b'file300\0%s\n') % (

    def testMatchesNonexistentFile(self):
        """Tests matches() for a small set of specific files, including one
        nonexistent file to make sure in only matches against existing files.
        """
        m = self.parsemanifest(20, A_DEEPER_MANIFEST)

        match = matchmod.exact(
            [b'a/b/c/bar.txt', b'a/b/d/qux.py', b'readme.txt', b'nonexistent']
        )
        m2 = m._matches(match)

        )

    def testMatchesNonexistentDirectory(self):
        """Tests matches() for a relpath match on a directory that doesn't
        actually exist."""
        m = self.parsemanifest(20, A_DEEPER_MANIFEST)

        match = matchmod.match(
            util.localpath(b'/repo'), b'', [b'a/f'], default=b'relpath'
        )
        m2 = m._matches(match)

        self.assertEqual([], m2.keys())

    def testMatchesExactLarge(self):
        """Tests matches() for files matching a large list of exact files."""
        m = self.parsemanifest(20, A_HUGE_MANIFEST)

        flist = m.keys()[80:300]
        match = matchmod.exact(flist)
        m2 = m._matches(match)

        self.assertEqual(flist, m2.keys())

    def testMatchesFull(self):
        '''Tests matches() for what should be a full match.'''
        m = self.parsemanifest(20, A_DEEPER_MANIFEST)

        match = matchmod.match(util.localpath(b'/repo'), b'', [b''])
        m2 = m._matches(match)

        self.assertEqual(m.keys(), m2.keys())

    def testMatchesDirectory(self):
        """Tests matches() on a relpath match on a directory, which should
        match against all files within said directory."""
        m = self.parsemanifest(20, A_DEEPER_MANIFEST)

        match = matchmod.match(
            util.localpath(b'/repo'), b'', [b'a/b'], default=b'relpath'
        )
        m2 = m._matches(match)

    def testMatchesExactPath(self):
        """Tests matches() on an exact match on a directory, which should
        result in an empty manifest because you can't perform an exact match
        against a directory."""
        m = self.parsemanifest(20, A_DEEPER_MANIFEST)

        match = matchmod.exact([b'a/b'])
        m2 = m._matches(match)

        self.assertEqual([], m2.keys())

    def testMatchesCwd(self):
        """Tests matches() on a relpath match with the current directory ('.')
        when not in the root directory."""
        m = self.parsemanifest(20, A_DEEPER_MANIFEST)

        match = matchmod.match(
            util.localpath(b'/repo'), b'a/b', [b'.'], default=b'relpath'
        )
        m2 = m._matches(match)

        )

    def testMatchesWithPattern(self):
        """Tests matches() for files matching a pattern that reside
        deeper than the specified directory."""
        m = self.parsemanifest(20, A_DEEPER_MANIFEST)

        match = matchmod.match(util.localpath(b'/repo'), b'', [b'a/b/*/*.txt'])
        m2 = m._matches(match)

        self.assertEqual(
            [b'a/b/c/bar.txt', b'a/b/c/foo.txt', b'a/b/d/ten.txt'], m2.keys()
        )


class testmanifestdict(unittest.TestCase, basemanifesttests):
    def parsemanifest(self, nodelen, text):
        return manifestmod.manifestdict(nodelen, text)

    def testManifestLongHashes(self):
        m = self.parsemanifest(32, b'a\0' + b'f' * 64 + b'\n')
        self.assertEqual(binascii.unhexlify(b'f' * 64), m[b'a'])

    def testObviouslyBogusManifest(self):
        # This is a 163k manifest that came from oss-fuzz. It was a
        # timeout there, but when run normally it doesn't seem to
        # present any particular slowness.

            b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00'
            b'\x00\x00\xc0\x8aey\x1d}\x01\xd8\xe0\xb9\xf3\xde\x1b\xcf\x17'
            b'\xac\xbe'
        )
        with self.assertRaises(ValueError):
            self.parsemanifest(20, data)


class testtreemanifest(unittest.TestCase, basemanifesttests):
    def parsemanifest(self, nodelen, text):
        return manifestmod.treemanifest(sha1nodeconstants, b'', text)

    def testWalkSubtrees(self):
        m = self.parsemanifest(20, A_DEEPER_MANIFEST)

        dirs = [s._dir for s in m.walksubtrees()]
        self.assertEqual(
            sorted(
                [b'', b'a/', b'a/c/', b'a/d/', b'a/b/', b'a/b/c/', b'a/b/d/']